{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T19:38:32Z","timestamp":1784921912963,"version":"3.55.0"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,10,29]],"date-time":"2021-10-29T00:00:00Z","timestamp":1635465600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,10,29]],"date-time":"2021-10-29T00:00:00Z","timestamp":1635465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100013407","name":"netherlands escience center","doi-asserted-by":"publisher","award":["ASDI.2017.030"],"award-info":[{"award-number":["ASDI.2017.030"]}],"id":[{"id":"10.13039\/100013407","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"published-print":{"date-parts":[[2021,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Mass spectrometry data is one of the key sources of information in many workflows in medicine and across the life sciences. Mass fragmentation spectra are generally considered to be characteristic signatures of the chemical compound they originate from, yet the chemical structure itself usually cannot be easily deduced from the spectrum. Often, spectral similarity measures are used as a proxy for structural similarity but this approach is strongly limited by a generally poor correlation between both metrics. Here, we propose MS2DeepScore: a novel Siamese neural network to predict the structural similarity between two chemical structures solely based on their MS\/MS fragmentation spectra. Using a cleaned dataset of &gt;\u2009100,000 mass spectra of about 15,000 unique known compounds, we trained MS2DeepScore to predict structural similarity scores for spectrum pairs with high accuracy. In addition, sampling different model varieties through Monte-Carlo Dropout is used to further improve the predictions and assess the model\u2019s prediction uncertainty. On 3600 spectra of 500 unseen compounds, MS2DeepScore is able to identify highly-reliable structural matches and to predict Tanimoto scores for pairs of molecules based on their fragment spectra with a root mean squared error of about 0.15. Furthermore, the prediction uncertainty estimate can be used to select a subset of predictions with a root mean squared error of about 0.1. Furthermore, we demonstrate that MS2DeepScore outperforms classical spectral similarity measures in retrieving chemically related compound pairs from large mass spectral datasets, thereby illustrating its potential for spectral library matching. Finally, MS2DeepScore can also be used to create chemically meaningful mass spectral embeddings that could be used to cluster large numbers of spectra. Added to the recently introduced unsupervised Spec2Vec metric, we believe that machine learning-supported mass spectral similarity measures have great potential for a range of metabolomics data processing pipelines.<\/jats:p>","DOI":"10.1186\/s13321-021-00558-4","type":"journal-article","created":{"date-parts":[[2021,10,29]],"date-time":"2021-10-29T12:02:33Z","timestamp":1635508953000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":171,"title":["MS2DeepScore: a novel deep learning similarity measure to compare tandem mass spectra"],"prefix":"10.1186","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3535-9406","authenticated-orcid":false,"given":"Florian","family":"Huber","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1250-6968","authenticated-orcid":false,"given":"Sven","family":"van der Burg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9340-5511","authenticated-orcid":false,"given":"Justin J. J.","family":"van der Hooft","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7635-9533","authenticated-orcid":false,"given":"Lars","family":"Ridder","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,10,29]]},"reference":[{"issue":"2","key":"558_CR1","doi-asserted-by":"publisher","first-page":"31","DOI":"10.3390\/metabo8020031","volume":"8","author":"I Bla\u017eenovi\u0107","year":"2018","unstructured":"Bla\u017eenovi\u0107 I, Kind T, Ji J, Fiehn O (2018) software tools and approaches for compound identification of LC-MS\/MS data in metabolomics. Metabolites 8(2):31","journal-title":"Metabolites"},{"issue":"1","key":"558_CR2","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1038\/nmeth.4512","volume":"15","author":"Z Lai","year":"2018","unstructured":"Lai Z, Tsugawa H, Wohlgemuth G, Mehta S, Mueller M, Zheng Y et al (2018) Identifying metabolites by integrating metabolome databases with mass spectrometry cheminformatics. Nat Methods 15(1):53\u201356","journal-title":"Nat Methods"},{"issue":"7","key":"558_CR3","doi-asserted-by":"publisher","first-page":"960","DOI":"10.1039\/C9NP00006B","volume":"36","author":"AEF Ramos","year":"2019","unstructured":"Ramos AEF, Evanno L, Poupon E, Champy P, Beniddir MA (2019) Natural products targeting strategies involving molecular networking: different manners, one goal. Nat Prod Rep 36(7):960\u2013980","journal-title":"Nat Prod Rep"},{"issue":"6","key":"558_CR4","doi-asserted-by":"publisher","first-page":"1954","DOI":"10.1038\/s41596-020-0317-5","volume":"15","author":"AT Aron","year":"2020","unstructured":"Aron AT, Gentry EC, McPhail KL, Nothias L-F, Nothias-Esposito M, Bouslimani A et al (2020) Reproducible molecular networking of untargeted mass spectrometry data using GNPS. Nat Protoc 15(6):1954\u20131991","journal-title":"Nat Protoc"},{"issue":"12","key":"558_CR5","doi-asserted-by":"publisher","first-page":"2692","DOI":"10.1007\/s13361-017-1797-6","volume":"28","author":"JE Scholl\u00e9e","year":"2017","unstructured":"Scholl\u00e9e JE, Schymanski EL, Stravs MA, Gulde R, Thomaidis NS, Hollender J (2017) Similarity of high-resolution tandem mass spectrometry spectra of structurally related micropollutants and transformation products. J Am Soc Mass Spectrom 28(12):2692\u20132704","journal-title":"J Am Soc Mass Spectrom"},{"issue":"2","key":"558_CR6","doi-asserted-by":"publisher","first-page":"e1008724","DOI":"10.1371\/journal.pcbi.1008724","volume":"17","author":"F Huber","year":"2021","unstructured":"Huber F, Ridder L, Verhoeven S, Spaaks JH, Diblen F, Rogers S et al (2021) Spec2Vec: improved mass spectral similarity scoring through learning of structural relationships. PLOS Comput Biol 17(2):e1008724","journal-title":"PLOS Comput Biol"},{"issue":"1","key":"558_CR7","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1186\/1758-2946-5-26","volume":"5","author":"S Riniker","year":"2013","unstructured":"Riniker S, Landrum GA (2013) Open-source platform to benchmark fingerprints for ligand-based virtual screening. J Cheminform 5(1):26","journal-title":"J Cheminform"},{"issue":"2","key":"558_CR8","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1517\/17460441.2016.1117070","volume":"11","author":"I Muegge","year":"2016","unstructured":"Muegge I, Mukherjee P (2016) An overview of molecular fingerprint similarity search in virtual screening. Expert Opin Drug Discov 11(2):137\u2013148","journal-title":"Expert Opin Drug Discov"},{"issue":"41","key":"558_CR9","doi-asserted-by":"publisher","first-page":"12549","DOI":"10.1073\/pnas.1516878112","volume":"112","author":"RR da Silva","year":"2015","unstructured":"da Silva RR, Dorrestein PC, Quinn RA (2015) Illuminating the dark matter in metabolomics. Proc Natl Acad Sci 112(41):12549\u201312550","journal-title":"Proc Natl Acad Sci"},{"issue":"41","key":"558_CR10","doi-asserted-by":"publisher","first-page":"12580","DOI":"10.1073\/pnas.1509788112","volume":"112","author":"K D\u00fchrkop","year":"2015","unstructured":"D\u00fchrkop K, Shen H, Meusel M, Rousu J, B\u00f6cker S (2015) Searching molecular structure databases with tandem mass spectra using CSI:FingerID. Proc Natl Acad Sci U S A 112(41):12580\u201312585","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"13","key":"558_CR11","doi-asserted-by":"publisher","first-page":"8649","DOI":"10.1021\/acs.analchem.0c01450","volume":"92","author":"H Ji","year":"2020","unstructured":"Ji H, Deng H, Lu H, Zhang Z (2020) Predicting a molecular fingerprint from an electron ionization mass spectrum with deep neural networks. Anal Chem 92(13):8649\u20138653","journal-title":"Anal Chem"},{"issue":"10","key":"558_CR12","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/s11306-020-01726-7","volume":"16","author":"Z Fan","year":"2020","unstructured":"Fan Z, Alley A, Ghaffari K, Ressom HW (2020) MetFID: artificial neural network-based compound fingerprint prediction for metabolite annotation. Metabolomics 16(10):104","journal-title":"Metabolomics"},{"key":"558_CR13","doi-asserted-by":"publisher","DOI":"10.1002\/rcm.9120","author":"Y Liu","year":"2021","unstructured":"Liu Y, Vijlder TD, Bittremieux W, Laukens K, Heyndrickx W (2021) Current and future deep learning algorithms for tandem mass spectrometry (MS\/MS)-based small molecule structure elucidation. Rapid Commun Mass Spectrom. https:\/\/doi.org\/10.1002\/rcm.9120","journal-title":"Rapid Commun Mass Spectrom"},{"issue":"9","key":"558_CR14","doi-asserted-by":"publisher","first-page":"5629","DOI":"10.1021\/acs.analchem.8b05405","volume":"91","author":"H Ji","year":"2019","unstructured":"Ji H, Xu Y, Lu H, Zhang Z (2019) Deep MS\/MS-aided structural-similarity scoring for unknown metabolite identification. Anal Chem 91(9):5629\u20135637","journal-title":"Anal Chem"},{"key":"558_CR15","unstructured":"Bromley J, Guyon I, LeCun Y, S\u00e4ckinger E, Shah R (1993) Signature verification using a \u201cSiamese\u201d time delay neural network. In: Proceedings of the 6th international conference on neural information processing systems. San Francisco: Morgan Kaufmann Publishers Inc., pp 737\u201344. (NIPS\u201993)"},{"issue":"8","key":"558_CR16","doi-asserted-by":"publisher","first-page":"828","DOI":"10.1038\/nbt.3597","volume":"34","author":"M Wang","year":"2016","unstructured":"Wang M, Carver JJ, Phelan VV, Sanchez LM, Garg N, Peng Y et al (2016) Sharing and community curation of mass spectrometry data with GNPS. Nat Biotechnol 34(8):828\u2013837","journal-title":"Nat Biotechnol"},{"key":"558_CR17","unstructured":"Gal Y, Ghahramani Z (2016) Dropout as a bayesian approximation: representing model uncertainty in deep learning. ArXiv150602142 Cs Stat. http:\/\/arxiv.org\/abs\/1506.02142. Accessed 1 Apr 2021"},{"issue":"52","key":"558_CR18","doi-asserted-by":"publisher","first-page":"2411","DOI":"10.21105\/joss.02411","volume":"5","author":"F Huber","year":"2020","unstructured":"Huber F, Verhoeven S, Meijer C, Spreeuw H, Castilla EMV, Geng C et al (2020) matchms\u2014processing and similarity evaluation of mass spectrometry data. J Open Source Softw 5(52):2411","journal-title":"J Open Source Softw"},{"issue":"1","key":"558_CR19","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1021\/ci00057a005","volume":"28","author":"D Weininger","year":"1988","unstructured":"Weininger D (1988) SMILES, a chemical language and information system.1. Introduction to methodology and encoding rules. J Chem Inf Comput Sci 28(1):31\u201336","journal-title":"J Chem Inf Comput Sci"},{"issue":"1","key":"558_CR20","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1186\/s13321-015-0068-4","volume":"7","author":"SR Heller","year":"2015","unstructured":"Heller SR, McNaught A, Pletnev I, Stein S, Tchekhovskoi D (2015) InChI, the IUPAC international chemical identifier. J Cheminform 7(1):23","journal-title":"J Cheminform"},{"issue":"1","key":"558_CR21","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1186\/s13321-020-00445-4","volume":"12","author":"A Capecchi","year":"2020","unstructured":"Capecchi A, Probst D, Reymond J-L (2020) One molecular fingerprint to rule them all: drugs, biomolecules, and the metabolome. J Cheminform 12(1):43","journal-title":"J Cheminform"},{"issue":"1","key":"558_CR22","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1021\/ci800249s","volume":"49","author":"A Bender","year":"2009","unstructured":"Bender A, Jenkins JL, Scheiber J, Sukuru SCK, Glick M, Davies JW (2009) How similar are similarity searching methods? a principal component analysis of molecular descriptor space. J Chem Inf Model 49(1):108\u2013119","journal-title":"J Chem Inf Model"},{"key":"558_CR23","unstructured":"Landrum G. RDKit: open-source cheminformatics. https:\/\/zenodo.org\/record\/3732262#.YXFhdhxCQ2w"},{"issue":"1","key":"558_CR24","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1186\/s13321-015-0069-3","volume":"7","author":"D Bajusz","year":"2015","unstructured":"Bajusz D, R\u00e1cz A, H\u00e9berger K (2015) Why is Tanimoto index an appropriate choice for fingerprint-based similarity calculations? J Cheminform 7(1):20","journal-title":"J Cheminform"},{"issue":"1","key":"558_CR25","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.aca.2004.04.014","volume":"516","author":"W Demuth","year":"2004","unstructured":"Demuth W, Karlovits M, Varmuza K (2004) Spectral similarity versus structural similarity: mass spectrometry. Anal Chim Acta 516(1):75\u201385","journal-title":"Anal Chim Acta"},{"issue":"26","key":"558_CR26","doi-asserted-by":"publisher","first-page":"E1743","DOI":"10.1073\/pnas.1203689109","volume":"109","author":"J Watrous","year":"2012","unstructured":"Watrous J, Roach P, Alexandrov T, Heath BS, Yang JY, Kersten RD et al (2012) Mass spectral molecular networking of living microbial colonies. Proc Natl Acad Sci U S A 109(26):E1743-1752","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"424","key":"558_CR27","doi-asserted-by":"publisher","first-page":"1273","DOI":"10.1080\/01621459.1993.10476408","volume":"88","author":"PJ Rousseeuw","year":"1993","unstructured":"Rousseeuw PJ, Croux C (1993) Alternatives to the median absolute deviation. J Am Stat Assoc 88(424):1273\u20131283","journal-title":"J Am Stat Assoc"},{"issue":"86","key":"558_CR28","first-page":"2579","volume":"9","author":"L van der Maaten","year":"2008","unstructured":"van der Maaten L, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res 9(86):2579\u20132605","journal-title":"J Mach Learn Res"},{"issue":"85","key":"558_CR29","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O et al (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12(85):2825\u20132830","journal-title":"J Mach Learn Res"},{"issue":"1","key":"558_CR30","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1186\/s13321-016-0174-y","volume":"8","author":"Y Djoumbou Feunang","year":"2016","unstructured":"Djoumbou Feunang Y, Eisner R, Knox C, Chepelev L, Hastings J, Owen G et al (2016) ClassyFire: automated chemical classification with a comprehensive, computable taxonomy. J Cheminform 8(1):61","journal-title":"J Cheminform"},{"key":"558_CR31","doi-asserted-by":"publisher","DOI":"10.1021\/acs.analchem.0c04834","author":"S Xing","year":"2021","unstructured":"Xing S, Jiao Y, Salehzadeh M, Soma KK, Huan T (2021) SteroidXtract: deep learning-based pattern recognition enables comprehensive and rapid extraction of steroid-like metabolic features for automated biology-driven metabolomics. Anal Chem. https:\/\/doi.org\/10.1021\/acs.analchem.0c04834","journal-title":"Anal Chem"},{"key":"558_CR32","first-page":"1","volume":"39","author":"K D\u00fchrkop","year":"2020","unstructured":"D\u00fchrkop K, Nothias L-F, Fleischauer M, Reher R, Ludwig M, Hoffmann MA et al (2020) Systematic classification of unknown metabolites using high-resolution fragmentation mass spectra. Nat Biotechnol 39:1\u201310","journal-title":"Nat Biotechnol"},{"key":"558_CR33","doi-asserted-by":"crossref","unstructured":"Kim H, Wang M, Leber C, Nothias L-F, Reher R, Kang KB, et al (2020) NPClassifier: a deep neural network-based structural classification tool for natural products. https:\/\/www.articles\/preprint\/NPClassifier_A_Deep_Neural_Network-Based_Structural_Classification_Tool_for_Natural_Products\/12885494\/1. Accessed 3 Apr 2021","DOI":"10.26434\/chemrxiv.12885494"},{"key":"558_CR34","doi-asserted-by":"publisher","DOI":"10.1101\/2020.07.21.214197v2","author":"M Bertoni","year":"2020","unstructured":"Bertoni M, Duran-Frigola M, Badia-i-Mompel P, Pauls E, Orozco-Ruiz M, Guitart-Pla O et al (2020) Bioactivity descriptors for uncharacterized compounds. bioRxiv. https:\/\/doi.org\/10.1101\/2020.07.21.214197v2","journal-title":"bioRxiv"},{"issue":"2","key":"558_CR35","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1038\/s41587-020-0700-3","volume":"39","author":"AA Aksenov","year":"2021","unstructured":"Aksenov AA, Laponogov I, Zhang Z, Doran SLF, Belluomo I, Veselkov D et al (2021) Auto-deconvolution and molecular networking of gas chromatography\u2013mass spectrometry data. Nat Biotechnol 39(2):169\u2013173","journal-title":"Nat Biotechnol"},{"issue":"4","key":"558_CR36","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1038\/s41592-019-0344-8","volume":"16","author":"K D\u00fchrkop","year":"2019","unstructured":"D\u00fchrkop K, Fleischauer M, Ludwig M, Aksenov AA, Melnik AV, Meusel M et al (2019) SIRIUS 4: a rapid tool for turning tandem mass spectra into metabolite structure information. Nat Methods 16(4):299\u2013302","journal-title":"Nat Methods"},{"issue":"1","key":"558_CR37","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1186\/s13321-018-0302-y","volume":"10","author":"A R\u00e1cz","year":"2018","unstructured":"R\u00e1cz A, Bajusz D, H\u00e9berger K (2018) Life beyond the Tanimoto coefficient: similarity measures for interaction fingerprints. J Cheminform 10(1):48","journal-title":"J Cheminform"},{"issue":"5","key":"558_CR38","doi-asserted-by":"publisher","first-page":"3156","DOI":"10.1021\/acs.analchem.7b04424","volume":"90","author":"C Guijas","year":"2018","unstructured":"Guijas C, Montenegro-Burke JR, Domingo-Almenara X, Palermo A, Warth B, Hermann G et al (2018) METLIN: a technology platform for identifying knowns and unknowns. Anal Chem 90(5):3156\u20133164","journal-title":"Anal Chem"},{"key":"558_CR39","doi-asserted-by":"publisher","unstructured":"Kramida A, Ralchenko Y, Reader J, NIST ASD Team (2020) NIST Atomic Spectra Database (ver. 5.8). https:\/\/doi.org\/10.18434\/T4W30F","DOI":"10.18434\/T4W30F"},{"key":"558_CR40","doi-asserted-by":"publisher","DOI":"10.1101\/483263v1","author":"DH May","year":"2018","unstructured":"May DH, Bilmes J, Noble WS (2018) A learned embedding for efficient joint analysis of millions of mass spectra. bioRxiv. https:\/\/doi.org\/10.1101\/483263v1","journal-title":"bioRxiv"},{"issue":"23","key":"558_CR41","doi-asserted-by":"publisher","first-page":"13900","DOI":"10.1021\/acs.analchem.8b03099","volume":"90","author":"F Olivon","year":"2018","unstructured":"Olivon F, Elie N, Grelier G, Roussi F, Litaudon M, Touboul D (2018) MetGem software for the generation of molecular networks based on the t-SNE algorithm. Anal Chem 90(23):13900\u201313908","journal-title":"Anal Chem"},{"issue":"D1","key":"558_CR42","doi-asserted-by":"publisher","first-page":"D1102","DOI":"10.1093\/nar\/gky1033","volume":"47","author":"S Kim","year":"2019","unstructured":"Kim S, Chen J, Cheng T, Gindulyte A, He J, He S et al (2019) PubChem 2019 update: improved access to chemical data. Nucleic Acids Res 47(D1):D1102\u2013D1109","journal-title":"Nucleic Acids Res"},{"key":"558_CR43","unstructured":"Swain M, Sj\u00f6gren R, Zachcp, Yi H, Lazzaro L, Dahlgren B (2017) mcs07\/PubChemPy: PubChemPy v1.0.4. Zenodo. https:\/\/zenodo.org\/record\/541438#.Xyq_ROexUUE. Accessed 5 Aug 2020"},{"key":"558_CR44","unstructured":"Goodfellow I, Bengio Y, Courville A (2016) Deep learning. The MIT Press. http:\/\/www.deeplearningbook.org. Accessed 1 Apr 2021"},{"key":"558_CR45","unstructured":"Kingma DP, Adam BJ (2017) A method for stochastic optimization. ArXiv14126980 Cs. http:\/\/arxiv.org\/abs\/1412.6980. Accessed 2 Apr 2021"},{"key":"558_CR46","first-page":"87","volume-title":"Position das","author":"T Kluyver","year":"2016","unstructured":"Kluyver T, Ragan-Kelley B, P\u00e9rez F, Granger B, Bussonnier M et al (2016) Jupyter Notebooks\u2014a publishing format for reproducible computational workflows. In: Kluyver T (ed) Position das. IOS Press, Amsterdam, pp 87\u201390"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-021-00558-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-021-00558-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-021-00558-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,29]],"date-time":"2021-10-29T12:07:00Z","timestamp":1635509220000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-021-00558-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,29]]},"references-count":46,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["558"],"URL":"https:\/\/doi.org\/10.1186\/s13321-021-00558-4","relation":{},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,29]]},"assertion":[{"value":"9 July 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 September 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 October 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"84"}}